art-bashkirev/DistilBERT-Test
This model is a fine-tuned version of distilbert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.6089
- Epoch: 8
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 0.001, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Epoch |
|---|---|
| 0.6125 | 0 |
| 0.6085 | 1 |
| 0.6085 | 2 |
| 0.6090 | 3 |
| 0.6083 | 4 |
| 0.6089 | 5 |
| 0.6091 | 6 |
| 0.6108 | 7 |
| 0.6089 | 8 |
Framework versions
- Transformers 4.34.1
- TensorFlow 2.12.0
- Datasets 2.14.5
- Tokenizers 0.14.1